AI agents call list_topics to retrieve information from Gcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and enumerates Pub/Sub topics, which is a read-only operation with no side effects. It does not create, modify, delete, or trigger any actions on the topics themselves. The blast radius of misuse is minimal — an attacker gains visibility into topic names but cannot access their contents or perform actions on them without additional tools.
From the tool's definition Tool name is 'list_topics' and description states 'List Pub/Sub topics in a project' — a query operation that retrieves information about existing resources without modification.
Attacks that exploit this kind of access
List Pub/Sub topics in a project. It is categorised as a Read tool in the Gcp MCP Server, which means it retrieves data without modifying state.
Register the Gcp MCP server in PolicyLayer and add a rule for list_topics: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Gcp. Nothing to install.
list_topics is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_topics rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for list_topics. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
list_topics is provided by the Gcp MCP server (lokimcpuniverse/gcp-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →